#!/usr/bin/env python
# coding: utf-8

# # `popmon` introductory notebook

# This notebook contains examples of how to generate `popmon` reports from a pandas DataFrame.

# In[ ]:


# (optional) Adjust the jupyter notebook style for easier navigation of the reports
from IPython.core.display import display, HTML

# Wider notebook
display(HTML("<style>.container { width:80% !important; }</style>"))
# Cells are higher by default
display(HTML("<style>div.output_scroll { height: 44em; }</style>"))


# ## Setup `popmon` and load our dataset

# Install popmon (if not installed yet) in the current environment.

# In[ ]:


import sys
get_ipython().system('"{sys.executable}" -m pip install -q popmon')


# Import pandas and popmon, load and example dataset provided by popmon and show the first few results.

# In[ ]:


import pandas as pd
import popmon
from popmon import resources


# In[ ]:


df = pd.read_csv(resources.data("test.csv.gz"), parse_dates=["date"])


# In[ ]:


df.head()


# ## Reporting given a pandas.DataFrame

# In[ ]:


report = df.pm_stability_report(
    # Use the 'date' column as our time axis
    time_axis="date",
    # Create batches for every two weeks of data
    time_width="2w",
    # Select a subset of features
    features=["date:age", "date:isActive", "date:eyeColor"],
)


# In[ ]:


report


# ### Regenerate the report
# You can change the report parameters without having to rerun the computational part of the pipeline using the `regenerate` method. For example: a short (limited) report will be generated since `extended_report` flag is set to `False`. If a user wants to configure which statistics she/he wants to see, `show_stats` argument has to be set accordingly.
# 
# Another option is to change the `plot_hist_n` parameter to control the number of histograms being displayed per feature.

# In[ ]:


report.regenerate(extended_report=False, plot_hist_n=3)


# ## Reporting given a histograms

# If the user would like to generate the report directly from histograms, then popmon also supports that.
# First, we generate histograms, (but we could load pre-generated histograms from a pickle or json file as well)

# In[ ]:


hists = df.pm_make_histograms(
    time_axis="date",
    time_width="2w",
    features=["date:age", "date:gender", "date:isActive"],
)


# In[ ]:


list(hists.keys())


# And then generate the report based on histograms:

# In[ ]:


report = popmon.stability_report(hists)


# In[ ]:


report